Salsabilah, Elina (2025) PREDIKSI HARGA DAGING AYAM BROILER DI JAWA TIMUR MENGGUNAKAN METODE XGBOOST DENGAN OPTIMASI OPTUNA. Undergraduate thesis, UPN Veteran Jawa Timur.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
21083010100_Cover.pdf Download (1MB) |
|
Text (Bab 1)
21083010100_Bab I.pdf Download (266kB) |
|
Text (Bab 2)
21083010100_Bab II.pdf Restricted to Repository staff only until 21 October 2027. Download (645kB) |
|
Text (Bab 3)
21083010100_Bab III.pdf Restricted to Repository staff only until 21 October 2027. Download (473kB) |
|
Text (Bab 4)
21083010100_Bab IV.pdf Restricted to Repository staff only until 21 October 2027. Download (6MB) |
|
Text (Bab 5)
21083010100_Bab V.pdf Download (234kB) |
|
Text (Daftar Pustaka)
21083010100_Daftar Pustaka.pdf Download (197kB) |
|
Text (Lampiran)
21083010100_Lampiran.pdf Restricted to Repository staff only Download (315kB) |
Abstract
Broiler chicken meat is one of the most widely consumed poultry commodities in Indonesia due to its affordable price and abundant availability. However, broiler chicken prices often experience significant fluctuations due to various factors, such as the price of animal feed, DOC (Day Old Chick), corn prices, seasonal patterns, and suboptimal distribution conditions. These price fluctuations create uncertainty that can be detrimental to farmers and consumers, so a more accurate prediction method is needed to support decision-making. This study uses the Extreme Gradient Boosting (XGBoost) algorithm optimized with Optuna to automatically tune hyperparameters. As a comparison, the Autoregressive Integrated Moving Average (ARIMA) model is used as a conventional time series method. The results show that the initial XGBoost model has quite good performance with an RMSE value of 472.25 and a MAPE of 0.43%. After hyperparameter optimization using Optuna, performance improved significantly with the RMSE decreasing to 304.29 and the MAPE to 0.31%. In contrast, the ARIMA model produced an RMSE of 1656.43 and a MAPE of 3.47%, indicating significantly lower accuracy. These findings demonstrate that XGBoost with Optuna optimization is superior in predicting broiler chicken prices compared to conventional methods and can be used as a basis for formulating price stabilization and supply management policies in Indonesia.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics Q Science > QA Mathematics > QA76.6 Computer Programming |
||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Data Science | ||||||||||||
| Depositing User: | Elina Salsabilah | ||||||||||||
| Date Deposited: | 24 Oct 2025 08:10 | ||||||||||||
| Last Modified: | 24 Oct 2025 08:10 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/45677 |
Actions (login required)
 |
View Item |